metadata
license: mit
base_model: microsoft/biogpt
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bioGPT_finetuned_ncbi
results: []
bioGPT_finetuned_ncbi
This model is a fine-tuned version of microsoft/biogpt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1880
- Precision: 0.4637
- Recall: 0.5448
- F1: 0.5010
- Accuracy: 0.9476
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1735 | 1.0 | 1358 | 0.2050 | 0.3990 | 0.4094 | 0.4041 | 0.9415 |
| 0.1086 | 2.0 | 2716 | 0.1800 | 0.4230 | 0.5354 | 0.4726 | 0.9463 |
| 0.07 | 3.0 | 4074 | 0.1880 | 0.4637 | 0.5448 | 0.5010 | 0.9476 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2